Prediction and optimization of processing parameters in wire and arc-based additively manufacturing of 316L stainless steel

Le, Van Thao; Doan, Quang Thanh; Si, Dinh; Bui, Manh Cuong; Tran, Hoang Son; Tran, Xuan Van; Nguyen, Van Anh Thi

doi:10.1007/s40430-022-03698-2

Cited by 20 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In TOPSIS method [12], the attributes (i.e., WTW, WTH, and ) were firstly placed in the deciding matrix DM = [Aij]mxn, where Aij is the j th objective in the i th experimental run, n is the objectives number, and m is the experimental runs number.…”

Section: Materials and Experiments Designmentioning

confidence: 99%

Multi-Objective Optimization for Weld Track Geometry in Wire-Arc Directed Energy Deposition of ER308L Stainless Steel

Nguyen¹,

Le²,

Pham³

et al. 2023

Journal of Machine Engineering

View full text Add to dashboard Cite

In this research, the weld track geometry in wire-arc DED (directed energy deposition) of ER308L stainless steel was predicted and optimized. The studied geometrical attributes of weld tracks include weld track width (WTW), weld track height (WTH), and contact angle (α). The experiment was designed based on Taguchi method with three variables (current I, voltage U, and weld velocity v) and four levels for each variable. The ANOVA was adopted to evaluate the accuracy of the models and impact levels of variables on the responses. The TOPSIS method was utilized to predict the optimal variables. The results indicated that the predicted models were built with high accuracy levels (R 2 = 98.92%, 98.77%, and 98.91% for WTW, WTH, and α, respectively). Among the studied variables, U features the highest effects on WTW and  with 78.56% and 69.90% of contribution, respectively, while v is the variable that has the most impact on WTH with 39.82% of contribution. The optimal variables predicted by TOPSIS were U = 23 V, I = 140 A, and v = 300 mm/min, which allows building components with stable and regular geometry.

show abstract

Section: Materials and Experiments Designmentioning

confidence: 99%

Multi-Objective Optimization for Weld Track Geometry in Wire-Arc Directed Energy Deposition of ER308L Stainless Steel

Nguyen¹,

Le²,

Pham³

et al. 2023

Journal of Machine Engineering

View full text Add to dashboard Cite

show abstract

“…This provides high deposition rates and significant cost‐effectiveness, making it suitable for the manufacture of large‐size parts. [ 11,12 ] At present, some studies have focused on the application of WAAM 316L in naval [ 13 ] and nuclear materials. [ 14 ] Owing to the advantages of fast forming speed and the ability to manufacture parts at a large scale, WAAM has gained considerable attention and shows potential for fabricating complex 316L steel components.…”

Section: Introductionmentioning

confidence: 99%

The Formability and Mechanical Properties of 316L Stainless Steel Fabricated by Pulsed Arc Swing Additive Manufacturing

Meng,

Pan,

et al. 2024

steel research int.

View full text Add to dashboard Cite

An austenitic stainless steel 316L deposition specimen is fabricated by cold metal transfer‐based swing arc additive manufacturing (CMT‐SAAM), and its formation, microstructure, and tensile properties are investigated. The results showed that the 316L deposited samples exhibited a multi‐layer structure with a small aspect ratio, and the surface forming accuracy is improved with the increase in the swing amplitude. The remelted zone near the interface is dominated by long grains perpendicular to the fusion line, whereas the deposited zone is dominated by columnar dendrites and shows an <100> orientation. Along the building and transverse direction of the swing deposits, the microhardness distribution is uniform. Compared with rollings and forgings, 316L deposited by using the CMT‐SAAM method has both a higher strength and toughness. The average ultimate tensile strength is 573 MPa, and the elongation at break is 52.6%. The high strength and toughness of 316L specimens are attributed to the fine microstructure, high‐density dislocations, and low‐angle grain boundaries (LAGBs) generated during the CMT‐SAAM process.

show abstract

“…Sarathchandra et al [10] evaluated the effects of the WS, welding current, and standoff distance on weld bead characteristics by response surface method in conjunction with ANOVA; they used MRA to establish a model between process parameters and weld bead quality. Le et al [11] used Grey-Relational Analysis (GRA) and Techniques for Order-Preferences by Similarity-to Ideal Solution (TOPSIS) methods to determine the optimal process parameters. FEM-based modelling can investigate how process parameters affect the dimensional accuracy of the component and optimize process parameters [12,13].…”

Section: Introductionmentioning

confidence: 99%

Modelling and Prediction of Process Parameters with Low Energy Consumption in Wire Arc Additive Manufacturing Based on Machine Learning

Zhang,

Bai,

Dong

et al. 2024

Metals

View full text Add to dashboard Cite

Wire arc additive manufacturing (WAAM) has attracted increasing interest in industry and academia due to its capability to produce large and complex metallic components at a high deposition rate. One of the basic tasks in WAAM is to determine appropriate process parameters, which will directly affect the morphology and quality of the weld bead. However, the selection of process parameters relies heavily on empirical data from trial-and-error experiments, which results in significant time and cost expenditures. This paper employed different machine learning models, including SVR, BPNN, and XGBoost, to predict process parameters for WAAM. Furthermore, the SVR model was optimized by the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithms. A 3D laser scanner was employed to obtain the weld bead’s point cloud, and the weld bead size was extracted using the point cloud processing algorithm as the training data. The K-fold cross-validation strategy was applied to train and validate machine learning models. The comparison results showed that PSO–SVR predicted process parameters with the highest precision, with the RMSE, R2, and MAE being 1.1670, 0.9879, and 0.8310, respectively. Based on the process parameters produced by PSO–SVR, an optimal process parameter combination was chosen by taking into comprehensive consideration the impacts of power consumption and efficiency. The effectiveness of the process parameter optimization method was proved through three groups of validation experiments, with the energy consumption of the first two groups decreasing by 10.68% and 11.47%, respectively.

show abstract

Prediction and optimization of processing parameters in wire and arc-based additively manufacturing of 316L stainless steel

Cited by 20 publications

References 50 publications

Multi-Objective Optimization for Weld Track Geometry in Wire-Arc Directed Energy Deposition of ER308L Stainless Steel

Multi-Objective Optimization for Weld Track Geometry in Wire-Arc Directed Energy Deposition of ER308L Stainless Steel

The Formability and Mechanical Properties of 316L Stainless Steel Fabricated by Pulsed Arc Swing Additive Manufacturing

Modelling and Prediction of Process Parameters with Low Energy Consumption in Wire Arc Additive Manufacturing Based on Machine Learning

Contact Info

Product

Resources

About